JP6762454B1 - Pitch pattern correction device, program and pitch pattern correction method - Google Patents

Abstract

In the voice pitch pattern, the partial pitch correction unit (210) that corrects a specific section and the pitch pattern that includes the corrected specific section specify the maximum value of the pitch included in the sentence ending phrase in the voice. At least one of the maximum pitch specifying part (203), the specified maximum value, and the pitch included in the sentence ending pitch section, which is the section corresponding to the phoneme at the end of the speech in the pitch pattern including the corrected specific section. A pitch pattern correction unit (209) that changes the speech style of the voice by correcting the pitch pattern including the corrected specific section according to one of them is provided.

Description

The present invention relates to a pitch pattern correction device, a program, and a pitch pattern correction method.

Conventionally, many techniques have been developed in which the pitch pattern of a declarative voice is corrected to generate a voice having another utterance style such as question tone, reminder, or intonation including personality.
In Patent Document 1, the maximum value is extracted from the end of the sentence of the pitch pattern, the reference pitch corresponding to the value between the maximum value and the pitch of the terminal prosody is calculated, and the value smaller than the reference pitch and the value larger than the reference pitch are set. A prosody correction method for correcting prosody by calculating the pitch at the end of a sentence is disclosed.

Japanese Unexamined Patent Publication No. 2008-15362

The conventional prosody correction method is configured so that a pitch smaller than the maximum value always occurs at the end of the sentence, and when the flat accent phrase is at the end of the sentence, a speech style in which the pitch such as a question tone continues to rise is generated. There is a problem that the pitch pattern becomes unnatural.

Therefore, an object of the present invention is to correct the pitch pattern so that the utterance style can be easily perceived naturally.

The pitch pattern correction device according to one aspect of the present invention is a partial pitch correction unit that corrects a specific section in a voice pitch pattern, and a sentence ending phrase in the voice in a pitch pattern including the corrected specific section. It is a section corresponding to the phoneme at the end of the sentence in the pitch pattern including the maximum pitch specifying unit that specifies the maximum value of the included pitch, the specified maximum value, and the corrected specific section. A pitch pattern correction unit that changes the speech style of the voice by correcting the pitch pattern including the corrected specific section according to at least one of the pitches included in the sentence end pitch section is provided . The specific section is characterized in that it is a section corresponding to a phoneme including the maximum value of the pitch included in the sentence ending phrase in the voice .

The program according to one aspect of the present invention includes a computer in a partial pitch correction unit that corrects a specific section in a voice pitch pattern, and a sentence ending phrase in the voice in a pitch pattern that includes the corrected specific section. It is a section corresponding to the phonology at the end of the sentence in the pitch pattern including the maximum pitch specifying part that specifies the maximum value of the pitch, the specified maximum value, and the corrected specific section. By correcting the pitch pattern including the corrected specific section according to at least one of the pitches included in the end-of-sentence pitch section, it functions as a pitch pattern correction unit that changes the speech style of the voice . The specific section is characterized in that it is a section corresponding to a phoneme including the maximum value of the pitch included in the sentence ending phrase in the voice .

The pitch pattern correction method according to one aspect of the present invention corrects a specific section in a voice pitch pattern, and in a pitch pattern including the corrected specific section, the pitch included in the sentence ending phrase in the voice. The pitch included in the end-of-sentence pitch section, which is the section corresponding to the end-of-sentence phonology of the voice in the pitch pattern including the specified maximum value and the corrected specific section. A pitch pattern correction method for changing the utterance style of the voice by correcting the pitch pattern including the corrected specific section according to at least one of them, wherein the specific section is in the voice. It is characterized in that it is a section corresponding to a phoneme including the maximum value of the pitch included in the sentence ending phrase .

According to one or more aspects of the present invention, the pitch pattern can be corrected so that the utterance style can be easily perceived naturally.

It is a block diagram which shows schematic structure of the pitch pattern correction apparatus which concerns on Embodiment 1. FIG. It is a block diagram which shows the hardware configuration example of the pitch pattern correction apparatus. It is a flowchart which shows the operation of the pitch pattern correction apparatus which concerns on Embodiment 1. FIG. It is the schematic which shows the 1st operation example of the pitch pattern correction part in Embodiment 1. It is the schematic which shows the 2nd operation example of the pitch pattern correction part in Embodiment 1. It is the schematic which shows an example of the pitch pattern correction method information in Embodiment 1. FIG. It is a block diagram which shows schematic structure of the pitch pattern correction apparatus which concerns on Embodiment 2. FIG. It is a flowchart which shows the operation of the pitch pattern correction apparatus which concerns on Embodiment 2. It is the schematic which shows the operation example of the maximum pitch section correction part. It is the schematic which shows an example of the maximum pitch section correction method information. It is the schematic which shows the operation example of the sentence end pitch section correction part. It is the schematic which shows an example of the sentence end pitch section correction method information. It is the schematic which shows the operation example of the pitch pattern correction part in Embodiment 2. It is the schematic which shows an example of the pitch pattern correction method information in Embodiment 2. It is a block diagram which shows schematic structure of the pitch pattern correction apparatus which concerns on Embodiment 3. FIG. It is a flowchart which shows the operation of the pitch pattern correction apparatus in Embodiment 3. It is the schematic which shows the operation example of the pitch pattern correction part in Embodiment 3. FIG. It is a block diagram which shows schematic structure of the pitch pattern correction apparatus which concerns on Embodiment 4. FIG. It is a flowchart which shows the operation of the pitch pattern correction apparatus which concerns on Embodiment 4. It is the schematic which shows the operation example of the pitch pattern correction part in Embodiment 4.

Embodiment 1.
FIG. 1 is a block diagram schematically showing the configuration of the pitch pattern correction device 100 according to the first embodiment.
The pitch pattern correction device 100 includes a voice information input unit 101, a pitch pattern acquisition unit 102, a maximum pitch identification unit 103, a sentence end pitch section identification unit 104, a language information input unit 105, and a language attribute information acquisition unit 106. A pitch correction coefficient input unit 107, a pitch pattern correction method storage unit 108, and a pitch pattern correction unit 109 are provided.

The voice information input unit 101 accepts input of voice information capable of at least specifying a voice pitch pattern. The voice information input unit 101 gives the input voice information to the pitch pattern acquisition unit 102.
As for the voice information, it suffices if the pitch pattern can be specified. For example, the voice information may be voice data indicating a voice spoken by a person, intermediate data for prosody control in a voice synthesizer, or a pitch pattern itself.

The pitch pattern acquisition unit 102 acquires a pitch pattern specified by the voice information given from the voice information input unit 101. The pitch pattern acquisition unit 102 gives the acquired pitch pattern to the maximum pitch identification unit 103, the sentence end pitch section identification unit 104, and the pitch pattern correction unit 109.
The pitch indicates the pitch of the sound, and the pitch pattern is a pattern indicating the change in the pitch of the sound. The pitch pattern is, for example, a pitch sampled at regular time intervals, a series combining time information and pitch, and a pitch of control points in a speech element unit (syllable, consonant-vowel or vowel-consonant, etc.) in speech synthesis. It may be as shown.

The maximum pitch specifying unit 103 specifies the maximum value of the pitch included in the end-of-speech phrase of the voice in the pitch pattern given by the pitch pattern acquisition unit 102, and generates the maximum pitch information indicating the specified maximum value. Then, the maximum pitch specifying unit 103 gives the maximum pitch information to the pitch pattern correction unit 109.

When the sentence ending phrase is an accent phrase, the maximum pitch specifying unit 103 can specify the sentence ending phrase as follows.
In a standard language, the pitch that has once started to fall does not rise again in one phrase, so the maximum pitch identification unit 103 estimates the phrase break at the peak and valley position of the pitch pattern transition, and thus ends the sentence. You can identify the phrase. Further, for example, when it is guaranteed that the last utterance is only one phrase like a simple word, the maximum pitch specifying unit 103 sets the end phrase after the section (pause section) where there is no pitch for a certain period of time or more. Can be regarded as. Further, when the pitch pattern is associated with the language information, the phrase delimiter can be known from the language information, so that the maximum pitch specifying unit 103 can specify the end-of-sentence phrase by referring to the language information. ..

Further, when the sentence end phrase is an exhalation phrase between the breathing pose and the sentence end, the maximum pitch specifying unit 103 can consider the section (for example, the pause section) or later where there is no pitch for a certain period of time or more as the sentence end phrase. ..

The maximum pitch information may be any information indicating the maximum value of the pitch in the sentence ending phrase. For example, the maximum pitch information may be the frequency information itself, or may be discretized or symbolized information. Further, the maximum pitch information may be not only one sample of the maximum value but also a value of a plurality of samples such as a phonological pitch pattern including the maximum value, or a statistical value such as an average value of a plurality of samples.

The sentence end pitch section specifying unit 104 identifies the sentence end pitch section, which is a section corresponding to the phoneme at the end of the speech in the pitch pattern given by the pitch pattern acquisition unit 102, and provides sentence end pitch information indicating the specified sentence end pitch section. Generate.
The sentence end pitch information may be any information that can identify the section in which the characteristic of the utterance style appears.

The language information input unit 105 accepts input of language information capable of at least specifying language attribute information related to the pitch pattern. The language information input unit 105 gives the input language information to the language attribute information acquisition unit 106.

The language information may be any information that can specify the language attribute information. For example, the linguistic information may be the linguistic attribute information itself, or may be a sentence mixed with kanji and kana in the case of Japanese, or information extracted by linguistic analysis from a notation such as an alphabet string in the case of English. ..

The language attribute information acquisition unit 106 acquires the language attribute information specified by the language information given by the language information input unit 105. The language attribute information acquisition unit 106 gives the acquired language attribute information to the pitch pattern correction unit 109.

The language attribute information may include information indicating a language attribute, which is a language attribute used to switch control when correcting a pitch pattern. For example, the linguistic attribute information may be a type of consonant with a trailing consonant such as accent position, voiced or unvoiced information, plosive consonant, affricate consonant, fricative consonant or no consonant, and is the phonological information itself indicating a phonological symbol string. May be good.

The pitch correction coefficient input unit 107 receives an input of a pitch correction coefficient for correcting the pitch pattern to make the voice of another utterance style. The pitch correction coefficient is information corresponding to the weight of the pitch correction amount, which is the correction amount for correcting the pitch, and may be one or more numerical information. The pitch correction coefficient input unit 107 gives the input pitch correction coefficient to the pitch pattern correction unit 109.

The pitch pattern correction method storage unit 108 stores pitch pattern correction method information indicating a pitch pattern correction method which is a pitch pattern correction method. It is assumed that the pitch pattern correction method information indicates the pitch pattern correction method for each language attribute. In other words, the pitch pattern correction method information indicates a plurality of language attributes and a plurality of pitch pattern correction methods each associated with each of the plurality of language attributes. The pitch pattern correction method information shall indicate a plurality of language attributes and a plurality of pitch pattern correction methods in which each of the plurality of language attributes is associated with each of the utterance styles to be changed. ..
The pitch pattern correction method may be, for example, the correction formula itself or a method indicating conditional branching in the program.

The pitch pattern correction unit 109 includes the maximum value indicated by the maximum pitch information given by the maximum pitch specifying unit 103 and the pitch included in the sentence end pitch section indicated by the sentence end pitch section information given by the sentence end pitch section specifying unit 104. The voice utterance style is changed by correcting the pitch pattern given by the pitch pattern acquisition unit 102 according to at least one of them. Here, the pitch pattern correction unit switches the pitch pattern correction method according to the language attribute indicated by the language attribute information given by the language attribute information acquisition unit 106.

The pitch pattern correction unit 109 corrects a correction target section, which is a predetermined section of the pitch pattern, according to the utterance style to be changed. Here, the correction target section is the sentence end pitch section indicated by the sentence end pitch section information given from the sentence end pitch section identification unit 104, but the first embodiment is not limited to such an example.

The pitch pattern correction unit 109 stores, for example, a pitch pattern correction method corresponding to the language attribute indicated by the language attribute information given by the language attribute information acquisition unit 106 in the pitch pattern correction method storage unit 108. Select from the correction method information.
Then, the pitch pattern correction unit 109 indicates the maximum value indicated by the maximum pitch information given by the maximum pitch specifying unit 103 and the sentence end pitch section information given by the sentence end pitch section specifying unit 104 according to the selected pitch pattern correction method. In the pitch pattern given by the pitch pattern acquisition unit 102, the pitch correction coefficient given by the pitch correction coefficient input unit 107 is used as necessary according to at least one of the pitches included in the end-of-sentence pitch section. The sentence end pitch section indicated by the sentence end pitch section information given by the pitch section specifying unit 104 is corrected.
The corrected pitch pattern is output as a corrected pitch pattern.

FIG. 2 is a block diagram showing a hardware configuration example of the pitch pattern correction device 100 according to the first embodiment.
As shown in FIG. 2, the pitch pattern correction device 100 includes a memory 131, a processor 132, a network interface (hereinafter referred to as a network I / F) 133, and a text input interface (hereinafter referred to as a text input I / F). It can be realized by a computer 130 including an image input interface (hereinafter referred to as an image input I / F) 135 and an acoustic input interface (hereinafter referred to as an acoustic input I / F) 136.

For example, the memory 131 stores a program that causes the processor 132 to function as a pitch pattern acquisition unit 102, a maximum pitch identification unit 103, a sentence end pitch section identification unit 104, a language attribute information acquisition unit 106, and a pitch pattern correction unit 109. Such a program may be provided through a network, or may be recorded and provided on a recording medium. That is, such a program may be provided as, for example, a program product.

Further, the memory 131 functions as a pitch pattern correction method storage unit 108 that stores pitch pattern correction method information.
Further, the memory 131 stores intermediate data such as pitch pattern, voice information, language attribute information, language information, maximum pitch information, sentence end pitch section information, pitch correction coefficient, and correction pitch pattern.
The memory 131, non-volatile memory, or volatile memory may be used.

The processor 132 is a circuit such as a CPU (Central Processing Unit) or a DSP (Digital Signal Processor) that reads a necessary program from the memory 131 and executes the program.

The network I / F 133 is an interface for communicating when referring to voice information, language information or pitch correction coefficient from data on the network or when inputting stream data, and is a voice information input unit 101 and a language information input unit. It can function as 105 or the pitch correction coefficient input unit 107. The network I / F 133 is unnecessary if it has a configuration that does not require communication.

The text input I / F 134 is an interface for inputting data on a PC or a network as a text string as an input means for voice information, language information, or pitch correction coefficient by using a keyboard, a mouse, or the like. It can function as an input unit 101, a language information input unit 105, or a pitch correction coefficient input unit 107. The text input I / F 134 is unnecessary if it has a configuration that does not require input by a keyboard, mouse, or the like.

The image input I / F135 is a display interface for designating data on a PC (Personal Computer) or a network as a means for inputting voice information, linguistic information, or pitch correction coefficient by GUI (Graphical User Interface). It can function as a voice information input unit 101, a language information input unit 105, or a pitch correction coefficient input unit 107. The image input I / F 135 is unnecessary if it has a configuration that does not require display on the display.

The acoustic input I / F 136 is an interface for inputting acoustics such as a microphone. The acoustic input I / F 136 can function as a voice information input unit. The acoustic input I / F 136 is unnecessary if the pitch pattern correction device 100 does not require recording by the microphone.

In FIG. 2, the memory 131 is arranged inside the computer 130, but the embodiment is not limited to such an example. For example, it may be an external memory such as a USB (Universal Serial Bus) memory, or it may be a storage device connected to a network. Further, the memory 131 may be composed of both the internal memory of the computer 130 and the external memory of the computer 130.

FIG. 3 is a flowchart showing the operation of the pitch pattern correction device 100.
First, the pitch pattern acquisition unit 102 receives at least voice information capable of specifying the pitch pattern from the voice information input unit 101, and acquires the pitch pattern specified by the voice information (S10). The acquired pitch pattern is given to the maximum pitch specifying unit 103, the sentence end pitch section specifying unit 104, and the pitch pattern correcting unit 109.

Here, the voice information input unit 101 may receive input of voice information from a device such as a microphone or a camera capable of acquiring an acoustic signal. Further, the voice information input unit 101 may read the voice information by selecting the data on the memory or the network by the user using a device such as a keyboard or a mouse. Further, the voice information input unit 101 may receive input as voice information of stream data acquired from another device or intermediate data of voice synthesis by performing communication.

Further, when the pitch pattern acquisition unit 102 extracts the pitch pattern from the voice data, a known method such as the cepstrum method may be used. Known methods such as the cepstrum method are described in the following documents.
Sadaoki Furui, "Voice Information Processing", 1st Edition, Morikita Publishing Co., Ltd., June 30, 1998, p. 22-26

Next, the language attribute information acquisition unit 106 receives the language information capable of specifying the required attribute of the language from the language information input unit 105, and acquires the language attribute information indicating the language attribute specified by the language information. (S11).

When the language information is not the language attribute information itself, the language attribute information acquisition unit 106 analyzes information such as reading or accent by a known natural language processing technique, specifies the language attribute, and identifies the specified language attribute. It suffices to generate the language attribute information indicating.
In this case, for example, the following documents describe known natural language processing techniques.
Yoshinori Kazaka, "Natural Language Processing in Speech Synthesis," Information Processing, Vol. 34, No. 10, 1993

When the voice information is voice data, the language attribute information acquisition unit 106 acquires the voice data from the language information input unit 105 or the voice information input unit 101, and uses a known voice recognition technique or the like to language the language. The information may be extracted and the language attribute information may be acquired from the extracted language information.
As a known speech recognition technique, there is a technique described in the following documents.
Sadaoki Furui, "Voice Information Processing", 1st Edition, Morikita Publishing Co., Ltd., June 30, 1998, p. 96-105

Next, the maximum pitch specifying unit 103 identifies the maximum value of the pitch in the trailing phrase from the pitch pattern, and generates maximum pitch information indicating the specified maximum value (S12). Then, the generated maximum pitch information is given to the pitch pattern correction unit 109.

For example, the maximum pitch specifying unit 103 may search for the maximum value among the pitch values included in the last frame of the pitch pattern and generate maximum pitch information indicating the value.
At this time, the maximum pitch specifying unit 103 may search by narrowing down to the vicinity of the accent position by receiving the language attribute information from the language attribute information acquisition unit 106.

Next, the sentence end pitch section specifying unit 104 identifies the section of the sentence end portion from the pitch pattern, and generates sentence end pitch section information indicating the section of the specified pitch pattern (S13). The generated sentence end pitch section information is given to the pitch pattern correction unit 109.

For example, the sentence end pitch section specifying unit 104 may specify the last phonological section of the pitch pattern.
Specifically, if the voice information includes the last phonological section information, or if the last phonological section can be estimated from the language attribute information acquired by the language attribute information acquisition unit 106, the sentence end pitch section The specific unit 104 may specify the section. For example, in Japanese, when the consonant of the last phonology is unvoiced, the pitch pattern continuous from the end can be the pitch pattern of the last vowel.

When there is no section information of the last phonology in the voice information, the sentence end pitch section specifying unit 104 traces back from the end in the pitch pattern, and the amount of change in the pitch with respect to the last pitch exceeds a certain threshold value. Information indicating the section up to, or the section from the end to the point where the pitch cannot be extracted may be used as the end-of-sentence pitch section information.

Next, the pitch correction coefficient input unit 107 gives the input pitch correction coefficient to the pitch pattern correction unit 109 (S14). Although the pitch correction coefficient is input in the first embodiment, the first embodiment is not limited to such an example. For example, when the pitch correction coefficient is a fixed value, the value may be included in the program functioning as the pitch pattern correction unit 109. In this case, the pitch correction coefficient input unit 107 may not be provided.

Next, the pitch pattern correction unit 109 corrects the pitch pattern (S15). Specifically, it is as follows.
The pitch pattern correction unit 109 refers to the pitch pattern correction method information and selects a pitch pattern correction method corresponding to the language attribute indicated by the language attribute information.
Then, the pitch pattern correction unit 109 indicates the maximum value indicated by the maximum pitch information given by the maximum pitch specifying unit 103 and the sentence end pitch section information given by the sentence end pitch section specifying unit 104 according to the selected pitch pattern correction method. The pitch correction coefficient given by the pitch correction coefficient input unit 107 is used as necessary according to at least one of the pitches included in the end-of-sentence pitch section, and among the pitch patterns given by the pitch pattern acquisition unit 102, The sentence end pitch section indicated by the sentence end pitch section information given by the sentence end pitch section identification unit 104 is corrected. The corrected pitch pattern is output as a corrected pitch pattern.

In the flowchart shown in FIG. 3, the processes of steps S11 to S13 can be performed in parallel, and may be performed from any step.

Further, by receiving the language attribute information acquired in S11, it may be possible to improve the extraction accuracy or reduce the processing amount in the maximum pitch specifying unit 103. In that case, after the processing in step S11, step S12 is performed. It should be done. In this case, the language attribute information is given from the language attribute information acquisition unit 106 to the maximum pitch specifying unit 103.

4 and 5 are schematic views showing an operation example of the pitch pattern correction unit 109.
Further, FIG. 6 is a schematic view showing an example of pitch pattern correction method information stored in the pitch pattern correction method storage unit 108. Here, as a language attribute, an example of selecting a pitch pattern correction method according to an accent position, which is an accent position in speech, is shown.

As shown in FIG. 6, the pitch pattern correction method information 108a is table-type information including a control target row 108b, a flat plate row 108c, and a non-flat plate row 108d.
The control target column 108b indicates a target to be corrected. Here, "start", "end", and "interpolation" are shown as examples of control targets. “Start” indicates the pitch at the beginning of the sentence end pitch section, and “end” indicates the pitch at the end of the sentence end pitch section. "Interpolation" indicates the pitch between the start pitch and the end pitch in the sentence end pitch section.

The flat plate sequence 108c indicates a pitch pattern correction method selected when the language attribute information indicates “flat plate”.
Here, "-", "maximum pitch x pitch correction coefficient", and "linear interpolation" are shown as the pitch pattern correction method for the "flat plate".
"-" Indicates that the control target in the same line is not corrected.
The "maximum pitch x pitch correction coefficient" is the value obtained by multiplying the maximum value of the pitch specified by the maximum pitch specifying unit 103 by the pitch correction coefficient given by the pitch correction coefficient input unit 107, and added to the control target of the same line. Indicates to do.
"Linear interpolation" indicates that the pitch value between the starting pitch of the sentence ending pitch section and the ending pitch is obtained by linear interpolation based on the starting pitch value and the ending pitch value. The value of the pitch at the beginning and the value of the pitch at the end when performing interpolation are the corrected values when correction is performed.

The non-plate pattern sequence 108d indicates a pitch pattern correction method selected when the language attribute information indicates “non-plate pattern”.
Here, "terminal pitch-starting pitch", "(maximum pitch-terminal pitch) x pitch correction coefficient", and "spline interpolation" are shown as "non-flat" pitch pattern correction methods.
"Terminal pitch-starting pitch" indicates that the value obtained by subtracting the value of the starting pitch from the value of the ending pitch of the sentence ending pitch section is added to the control target of the same line.
"(Maximum pitch-terminal pitch) x pitch correction coefficient" is given by the pitch correction coefficient input unit 107 to a value obtained by subtracting the value of the terminal pitch from the maximum value of the pitch specified by the maximum pitch specifying unit 103. It is shown that the value obtained by multiplying the pitch correction coefficient obtained is added to the controlled object in the same row.
"Spline interpolation" indicates that the pitch value between the starting pitch of the sentence ending pitch section and the ending pitch is obtained by spline interpolation based on the starting pitch value and the ending pitch value. The value of the pitch at the beginning and the value of the pitch at the end when performing interpolation are the corrected values when correction is performed.

FIGS. 4 (A) and 4 (B) are examples of correcting the pitch pattern of the word "hantai" having a flat accent and having linguistic attribute information of the number 4 mora to a question-like pitch pattern.

FIG. 4A shows a pitch pattern before correction.
In this case, since the attribute information indicates "flat plate", the pitch pattern correction unit 109 selects, for example, the pitch pattern correction method of the flat plate from the pitch pattern correction method information 108a shown in FIG.

Therefore, as shown in FIG. 4B, the pitch pattern correction unit 109 uses the value obtained by integrating the given pitch correction coefficient with the maximum value of the pitch as the value of the pitch at the end of the sentence end pitch section. The correction is made by adding. Further, the pitch pattern correction unit 109 uses the value of the end pitch and the value of the start pitch with respect to the value of the pitch between the start pitch and the end pitch in the pitch pattern of the sentence end pitch section. Linear interpolation is performed.

In FIGS. 5A and 5B, the pitch pattern of the non-flat word "Sogune", which has an accent on the first character and has linguistic attribute information of the number 3 mora, is corrected to a question-like pitch pattern. This is an example.

FIG. 5A shows a pitch pattern before correction.
In this case, since the language attribute information indicates "non-flat plate", the pitch pattern correction unit 109 selects, for example, the non-flat plate pitch pattern correction method from the pitch pattern correction method information 108a shown in FIG. To do.

Therefore, as shown in FIG. 5 (B), the pitch pattern correction unit 109 subtracts the value of the pitch at the beginning of the sentence end pitch section from the value of the pitch at the end of the sentence end pitch section, and sets the starting end. The correction is performed by adding to the value of the pitch of. As a result, the value of the pitch at the beginning of the pitch section at the end of the sentence is converted into the value of the pitch at the end before correction.
Further, the pitch pattern correction unit 109 adds the value obtained by integrating the given pitch correction coefficient to the difference between the maximum value of the pitch and the value of the pitch at the end of the sentence end pitch section to the value of the end pitch. Is making corrections.
Further, the pitch pattern correction unit 109 performs spline interpolation from the corrected value for the value of the pitch between the start pitch and the end pitch in the sentence end pitch section pitch pattern.

Note that FIGS. 4 and 5 show a case where the pitch pattern correction method is selected between the flat plate type accent and the non-flat plate type accent, but other language attribute information such as the type of consonant or the number of mora can be obtained. It may be used to select a pitch pattern correction method.
For example, the length of the pitch pattern that continues from the end differs depending on whether the consonant of the last phoneme is a voiced sound or an unvoiced sound. Therefore, for example, the pitch pattern correction method can be selected so that a voiced sound having a long pitch pattern has a gradual change and a voiced sound having a short pitch pattern has a sudden change.
Similarly, the pitch pattern correction method can be selected so that the change is gradual when the number of mora is short (when the number of phonemes is small) and suddenly when the number of mora is long.
Further, the phoneme information includes voiced information, unvoiced information, or information indicating the type of consonant, and the pitch pattern correction method may be selected using such information.

Further, in FIGS. 4 and 5, the pitch between the start pitch and the end pitch is interpolated by the selected pitch pattern correction method, but the first embodiment is limited to such an example. Not done. For example, the interpolation may be performed by a fixed method regardless of the pitch pattern correction method.

Further, in FIGS. 4 and 5, the pitch pattern of the sentence end pitch section is corrected, but the correction may be performed not only for the sentence end pitch section but also for the entire pitch pattern.

As described above, in the first embodiment, the pitch pattern correction method is selected according to the language attribute information. This makes it possible to select a pitch pattern correction method according to the linguistic attribute information even when the difference in pitch pattern between the declarative voice and the utterance style greatly differs depending on the linguistic attribute information such as the accent position, and the prosody. The accuracy of correction is improved, and a natural pitch pattern in which the utterance style is easily perceived can be realized.

Embodiment 2.
FIG. 7 is a block diagram schematically showing the configuration of the pitch pattern correction device 200 according to the second embodiment.
The pitch pattern correction device 200 includes a voice information input unit 101, a pitch pattern acquisition unit 102, a maximum pitch identification unit 203, a pitch correction coefficient input unit 107, a pitch pattern correction method storage unit 208, and a pitch pattern correction unit 209. And a partial pitch correction unit 210.
The voice information input unit 101, pitch pattern acquisition unit 102, and pitch correction coefficient input unit 107 of the pitch pattern correction device 200 according to the second embodiment are the voice information input unit 101, pitch pattern of the pitch pattern correction device 100 according to the first embodiment. This is the same as the acquisition unit 102 and the pitch correction coefficient input unit 107.
However, the pitch pattern acquisition unit 102 gives the acquired pitch pattern to the partial pitch correction unit 210 and the pitch pattern correction unit 209.

The partial pitch correction unit 210 corrects at least one specific section in the pitch pattern.
The partial pitch correction unit 210 includes a maximum pitch section extraction unit 211, a maximum pitch section correction method storage unit 212, a maximum pitch section correction unit 213, a sentence end pitch section extraction unit 214, and a sentence end pitch section correction method storage unit 216. , The sentence end pitch section correction unit 215 is provided.

The maximum pitch section extraction unit 211 extracts and extracts the pitch pattern of the maximum pitch section, which is a section corresponding to the phoneme including the maximum value of the pitch in the sentence ending phrase, in the pitch pattern given by the pitch pattern acquisition unit 102. Generates maximum pitch interval extraction information indicating the pitch pattern. The generated maximum pitch section extraction information is given to the maximum pitch section correction unit 213.
For example, the maximum pitch interval extraction information may be a pitch pattern of a phoneme corresponding to the maximum value of the pitch, or a pitch pattern of a phoneme corresponding to the maximum value of the pitch and a phoneme in the vicinity thereof. The maximum pitch interval extraction information may be the frequency itself, or may be discretized or symbolized information.

The maximum pitch section correction method storage unit 212 stores the maximum pitch section correction method information indicating the maximum pitch section correction method which is a correction method of the pitch pattern of the maximum pitch section.
The maximum pitch section correction method may be, for example, the correction formula itself or a method indicating conditional branching in the program.

The maximum pitch section correction unit 213 indicates the maximum pitch section indicated by the maximum pitch section information given from the maximum pitch section extraction unit 211 by the maximum pitch section correction method information stored in the maximum pitch section correction method storage unit 212. Correct according to the maximum pitch section correction method. Then, the maximum pitch section correction unit 213 generates correction maximum pitch section information indicating the corrected pitch pattern, and gives the correction maximum pitch section information to the maximum pitch identification unit 203 and the pitch pattern correction unit 209.

The sentence end pitch section extraction unit 214 extracts the pitch pattern of the sentence end pitch section, which is a section corresponding to the phoneme at the end of the sentence, in the pitch pattern given by the pitch pattern acquisition unit 102, and indicates the sentence end pitch indicating the extracted pitch pattern. Generate interval extraction information. The generated sentence end pitch section information is given to the sentence end pitch section correction unit 215.

The sentence end pitch section extraction information may be any information including the pitch pattern of the section in which the characteristic of the utterance style appears. For example, the sentence end pitch section extraction information may be a pitch pattern of the last phoneme, or a pitch pattern of the last phoneme and its vicinity. The sentence end pitch section extraction information may be the frequency itself, or may be discretized or symbolized information.

The sentence end pitch section correction method storage unit 216 stores sentence end pitch section correction method information indicating a sentence end pitch section correction method which is a method for correcting the pitch pattern of the sentence end pitch section.
The sentence end pitch interval correction method may be, for example, the correction formula itself or may indicate a conditional branch in the program.

The sentence end pitch section correction unit 215 indicates the sentence end section indicated by the sentence end pitch section information given from the sentence end pitch section extraction unit 214 by the sentence end pitch section correction method information stored in the sentence end pitch section correction method storage unit 216. Correct according to the sentence end pitch section correction method. Then, the sentence end pitch section correction unit 215 generates correction sentence end pitch section information indicating the corrected pitch pattern, and gives the correction sentence end pitch section information to the pitch pattern correction unit 209.

The maximum pitch specifying unit 203 specifies the maximum value of the pitch included in the sentence ending phrase in the voice in the pitch pattern including the specific section corrected by the partial pitch correction unit 210.
Specifically, the maximum pitch specifying unit 203 specifies the maximum value of the pitch from the pitch pattern indicated by the corrected maximum pitch section information given by the maximum pitch section correction unit 213, and the maximum pitch indicating the specified maximum value. Generate information. Then, the maximum pitch specifying unit 203 gives the maximum pitch information to the pitch pattern correction unit 209.

The pitch pattern correction method storage unit 208 stores pitch pattern correction method information indicating a pitch pattern correction method. In the second embodiment, the pitch pattern correction method information does not need to indicate the pitch pattern correction method for each language attribute, and the pitch pattern correction method may be defined for each utterance style to be changed.
The pitch pattern correction method may be, for example, the correction formula itself or a method indicating conditional branching in the program.

The pitch pattern correction unit 209 is corrected by the partial pitch correction unit 210 according to at least one of the maximum value indicated by the maximum pitch information given by the maximum pitch specific unit 203 and the pitch included in the sentence end pitch section. The voice utterance style is changed by correcting the pitch pattern including a specific section. Here, when the sentence end pitch section is corrected by the sentence end pitch section correction unit 215, the corrected pitch value is used.

Specifically, the pitch pattern correction unit 209 is indicated by the pitch pattern indicated by the correction maximum pitch section information given by the maximum pitch section correction unit 213 and the correction sentence end pitch section information given by the sentence end pitch section correction unit 215. A partially corrected pitch pattern is generated by synthesizing the pitch pattern with the pitch pattern given by the pitch pattern acquisition unit 102.

The pitch pattern correction unit 209 acquires a pitch pattern correction method according to the utterance style for correcting the partial correction pitch pattern from the pitch pattern correction method information stored in the pitch pattern correction method storage unit 108.
Then, the pitch pattern correction unit 209 responds to at least one of the maximum value indicated by the maximum pitch information given by the maximum pitch specific unit 203 and the pitch included in the sentence end pitch section by the acquired pitch pattern correction method. , Pitch correction coefficient The pitch correction coefficient given by the input unit 107 is used as necessary, and the section corresponding to the pitch pattern indicated by the corrected sentence end pitch section information given by the sentence end pitch section correction unit 215 (that is, the sentence end pitch section). ) Partial correction Pitch pattern is corrected.
The corrected partial correction pitch pattern is output as a correction pitch pattern.

The pitch pattern correction device 200 according to the second embodiment can also be realized by the computer 130 shown in FIG.
For example, the memory 131 stores a program that causes the processor 132 to function as a pitch pattern acquisition unit 102, a maximum pitch identification unit 203, a pitch pattern correction unit 109, and a partial pitch correction unit 210.

Further, the memory 131 includes a pitch pattern correction method storage unit 108 that stores pitch pattern correction method information, a maximum pitch section correction method storage unit 212 that stores maximum pitch section correction method information, and a sentence end that stores sentence end pitch section correction method information. It functions as a pitch section correction method storage unit 216.

FIG. 8 is a flowchart showing the operation of the pitch pattern correction device 200.
First, the pitch pattern acquisition unit 102 receives at least voice information capable of specifying the pitch pattern from the voice information input unit 101, and acquires the pitch pattern specified by the voice information (S20). The processing here is the same as the processing in step S10 shown in FIG. The acquired pitch pattern is given to the maximum pitch section extraction unit 211, the sentence end pitch section extraction unit 214, and the pitch pattern correction unit 209.

Next, the maximum pitch section extraction unit 211 extracts the pitch pattern of the maximum pitch section, which is the section corresponding to the rhyme including the maximum value of the pitch in the sentence ending phrase, from the given pitch pattern, and the extracted pitch pattern. The maximum pitch interval extraction information indicating is generated (S21). The generated maximum pitch section extraction information is given to the maximum pitch section correction unit 213.

Next, the sentence end pitch section extraction unit 214 extracts the pitch pattern of the sentence end pitch section including the sentence end pitch from the given pitch pattern, and generates sentence end pitch section extraction information indicating the extracted pitch pattern (S22). ). The generated sentence end pitch section information is given to the sentence end pitch section correction unit 215. The method of specifying the end-of-sentence pitch section is the same as in step S13 shown in FIG.

Next, the pitch correction coefficient input unit 107 gives the input pitch correction coefficient to the pitch pattern correction unit 209 (S23). The processing here is the same as in step S14 shown in FIG.

Next, the maximum pitch section correction unit 213 corrects the pitch pattern of the maximum pitch section indicated by the given maximum pitch section information according to the maximum pitch section correction method (S24). Then, the maximum pitch section correction unit 213 generates correction maximum pitch section information indicating the corrected pitch pattern, and gives the correction maximum pitch section information to the maximum pitch identification unit 203 and the pitch pattern correction unit 209.

Next, the sentence end pitch section correction unit 215 corrects the pitch pattern of the sentence end section indicated by the given sentence end pitch section information according to the sentence end pitch section correction method (S25). Then, the sentence end pitch section correction unit 215 generates correction sentence end pitch section information indicating the corrected pitch pattern, and gives the correction sentence end pitch section information to the pitch pattern correction unit 209.

Next, the maximum pitch specifying unit 203 specifies the maximum value of the pitch in the pitch pattern indicated by the given corrected maximum pitch section information, and generates the maximum pitch information indicating the specified maximum value (S26). Then, the maximum pitch specifying unit 203 gives the maximum pitch information to the pitch pattern correction unit 209.

Next, the pitch pattern correction unit 209 corrects the pitch pattern (S27). Specifically, it is as follows.
First, the pitch pattern correction unit 209 combines the pitch pattern indicated by the given correction maximum pitch section information and the pitch pattern indicated by the given correction sentence end pitch section information into the given pitch pattern. , Generate a partial correction pitch pattern.
Next, the pitch pattern correction unit 209 acquires a pitch pattern correction method corresponding to the utterance style for correcting the partial correction pitch pattern from the pitch pattern correction method information stored in the pitch pattern correction method storage unit 208.
Then, the pitch pattern correction unit 209 is a pitch correction coefficient input unit according to at least one of the maximum value indicated by the given maximum pitch information and the pitch included in the sentence end pitch section by the acquired pitch pattern correction method. The pitch correction coefficient given from 107 is used as necessary to correct the partial correction pitch pattern of the section corresponding to the pitch pattern indicated by the given correction sentence end pitch section information (S27).

In the flowchart shown in FIG. 8, the processes of steps S21 to S23 can be performed in parallel, and may be performed from any step.

FIG. 9 is a schematic view showing an operation example of the maximum pitch section correction unit 213.
Further, FIG. 10 is a schematic view showing an example of the maximum pitch section correction method information stored in the maximum pitch section correction method storage unit 212.

As shown in FIG. 10, the maximum pitch section correction method information 212a is table-type information including the utterance style sequence 212b and the maximum pitch section correction method row 212c.
The utterance style sequence 212b shows the utterance style generated by performing correction by the pitch pattern correction unit 209. Here, "declaration", "question", and "confirmation" are shown as utterance styles. “Flat” indicates that a flat pitch pattern is generated by performing correction in the pitch pattern correction unit 209. The "question" indicates that a question-like pitch pattern is generated by performing correction by the pitch pattern correction unit 209. “Confirmation” indicates that a confirmation-tone pitch pattern is generated by performing correction in the pitch pattern correction unit 209.

Maximum pitch section correction method Column 212c shows a maximum pitch section correction method which is a correction method for correcting the pitch included in the maximum pitch section according to the utterance style of the same row.

In FIGS. 9A and 9B, the pitch pattern of the non-flat word "Sogune", which has an accent in the first character and has linguistic attribute information of the number 3 mora, is corrected to a question-like pitch pattern. This is an example of the maximum pitch section correction method in the case.
FIG. 9A shows a pitch pattern before correction.
The maximum pitch section correction unit 213 selects the maximum pitch section correction method corresponding to the question tone from the maximum pitch section correction method information 212a shown in FIG. 10, and as shown in FIG. 9B, Correct the pitch in the maximum pitch section. Here, the maximum pitch section correction unit 213 multiplied the value by 1.2. In this example, the maximum pitch interval is the pitch of two samples of the phoneme "o", and each value is multiplied by 1.2.

FIG. 11 is a schematic view showing an operation example of the sentence end pitch section correction unit 215.
Further, FIG. 12 is a schematic diagram showing an example of sentence end pitch section correction method information stored in the sentence end pitch section correction method storage unit 216.

As shown in FIG. 12, the sentence end pitch section correction method information 216a is table-type information including the utterance style sequence 216b and the sentence end pitch section correction method sequence 216c.
The utterance style sequence 216b shows the utterance style generated by performing correction by the pitch pattern correction unit 209. Here, "declaration", "question", and "confirmation" are shown as utterance styles.

Sentence end pitch section correction method Column 216c shows a sentence end pitch section correction method which is a correction method for correcting the pitch included in the sentence end pitch section according to the utterance style of the same line.

In FIGS. 11A and 11B, the pitch pattern of the non-flat word "Sogune", which has an accent in the first character and has linguistic attribute information of the number 3 mora, is corrected to a question-like pitch pattern. This is an example of a sentence end pitch section correction method in the case.
FIG. 11A shows a pitch pattern before correction.
The sentence end pitch section correction unit 215 selects the sentence end pitch section correction method corresponding to the question tone from the sentence end pitch section correction method information 216a shown in FIG. 12, and as shown in FIG. 11 (B), Correct the pitch in the end-of-sentence pitch section. Here, the sentence end pitch section correction unit 215 multiplies the value by 0.9. In this example, the sentence end pitch section is the pitch of two samples of the phoneme "e", and each value is multiplied by 0.9.

When the correction target of the maximum pitch section correction unit 213 or the sentence end pitch section correction unit 215 is a plurality of samples, it is not necessary to set a uniform correction value, and a correction method may be set according to the sample position. .. Further, after correcting the starting pitch and the ending pitch included in the maximum pitch section or the sentence ending pitch section, the pitch between them may be interpolated. Further, if the value included in the maximum pitch section or the sentence end pitch section to be corrected is a statistical value, each sample may be corrected so that the statistical value follows the correction method.

FIG. 13 is a schematic view showing an operation example of the pitch pattern correction unit 209 according to the second embodiment.
Further, FIG. 14 is a schematic view showing an example of pitch pattern correction method information stored in the pitch pattern correction method storage unit 208.

As shown in FIG. 14, the pitch pattern correction method information 208a is table-type information including the utterance style sequence 208b and the pitch pattern correction method sequence 208c.
The utterance style sequence 208b shows the utterance style generated by performing correction by the pitch pattern correction unit 209. Here, "declaration", "question", and "confirmation" are shown as utterance styles.

Pitch pattern correction method Column 208c shows a pitch pattern correction method which is a correction method for correcting the pitch included in the partial correction pitch pattern according to the utterance style of the same row.

FIG. 13A shows a partially corrected pitch pattern generated by synthesizing the pitch pattern indicated by the corrected maximum pitch section information and the pitch pattern indicated by the corrected sentence end pitch section information into the pitch pattern. ..
The pitch pattern correction unit 209 selects a pitch pattern correction method corresponding to the question tone from the pitch pattern correction method information 208a shown in FIG. 14, and as shown in FIG. 13 (B), the end-sentence pitch section. Correct the pitch of. Here, the pitch pattern correction unit 209 performs pitch correction given by the pitch correction coefficient input unit 107 to a value obtained by subtracting the value of the pitch at the end of the sentence end pitch section from the maximum value of the pitch given by the maximum pitch identification unit 203. The value obtained by multiplying the coefficient is added to the value of the pitch at the end of the sentence end pitch section.

In the above-described second embodiment, both the correction of the maximum pitch section and the correction of the sentence end pitch section are carried out, but the second embodiment is not limited to such an example. For example, in the second embodiment, either the correction of the maximum pitch section or the correction of the sentence end pitch section may be performed.
If the maximum pitch section is not corrected, the maximum pitch section extraction unit 211, the maximum pitch section correction method storage unit 212, and the maximum pitch section correction unit 213 can be omitted. In this case, the maximum pitch specifying unit 203 may specify the maximum value of the sentence end phrase in the pitch pattern given by the pitch pattern acquisition unit 102, similarly to the maximum pitch specifying unit 103 in the first embodiment.

Further, in the second embodiment, the pitches of the maximum pitch section and the sentence end pitch section are corrected, but the section corresponding to the pitch at the beginning of the sentence end phrase or the section corresponding to the minimum value of the pitch of the sentence end phrase is corrected. May be done. It suffices to make it possible to select the section for correcting the pitch according to the utterance style to be changed.

Further, in the second embodiment, the maximum pitch correction method, the sentence end pitch correction method, or the pitch pattern correction method is selected to correct the pitch, but the second embodiment is based on such an example. Not limited. For example, when the utterance style to be corrected is decided, those correction methods can be fixed. In such a case, the maximum pitch section correction method storage unit 212, the sentence end pitch section correction method storage unit 216, and the pitch pattern correction method storage unit 208 can be omitted.

As described above, in the second embodiment, at least one of the maximum pitch section correction unit 213 and the sentence end pitch section correction unit 215 is provided and is configured to correct the pitch value, so that it is emphasized or emphasized by the utterance style. Correction including changing intonation is possible, and there is an effect that the perceptual accuracy of the utterance style of the generated pitch pattern can be improved.

Further, in the second embodiment, when the pitch pattern at another place such as the pitch at the beginning of the sentence ending phrase or the minimum value of the pitch is corrected, the intonation in the maximum pitch section or the sentence ending pitch section is performed. In addition, it is possible to make corrections in consideration of intonation, which has a strong influence on the perceptual accuracy for each utterance style, and there is an effect that the perceptual accuracy of the utterance style of the generated pitch pattern can be improved.

The pitch pattern correction device 200 according to the second embodiment includes a language information input unit 105, a language attribute information acquisition unit 106, and a pitch pattern correction method storage unit 108 of the pitch pattern correction device 100 according to the first embodiment. The correction unit 209 may switch the pitch pattern correction method according to the language attribute, as in the first embodiment.

Embodiment 3.
FIG. 15 is a block diagram schematically showing the configuration of the pitch pattern correction device 300 according to the third embodiment.
The pitch pattern correction device 300 includes a voice information input unit 101, a pitch pattern acquisition unit 102, a maximum pitch identification unit 103, a sentence end pitch section identification unit 104, a pitch correction coefficient input unit 107, and a pitch pattern correction method storage unit. It includes 208, a pitch pattern correction unit 309, a continuous length information input unit 320, and a pitch correction coefficient correction unit 321.

The voice information input unit 101, pitch pattern acquisition unit 102, maximum pitch identification unit 103, sentence end pitch section identification unit 104, and pitch correction coefficient input unit 107 of the pitch pattern correction device 300 according to the third embodiment are described in the first embodiment. This is the same as the voice information input unit 101, the pitch pattern acquisition unit 102, the maximum pitch identification unit 103, the sentence end pitch section identification unit 104, and the pitch correction coefficient input unit 107 of the pitch pattern correction device 100.
Further, the pitch pattern correction method storage unit 208 of the pitch pattern correction device 300 according to the third embodiment is the same as the pitch pattern correction method storage unit 208 of the pitch pattern correction device 200 according to the second embodiment.
However, the pitch correction coefficient input unit 107 gives the input pitch correction coefficient to the pitch correction coefficient correction unit 321.

As the prosody, the continuation length information input unit 320 inputs the continuation length, which is the length of the voice corresponding to the section for correcting the pitch pattern, in other words, the continuation length information indicating the continuation length of the section to be corrected by the prosody. receive. Here, in the third embodiment, the section to be corrected of the prosody is the sentence end pitch section. The continuation length information is given to the pitch correction coefficient correction unit 321.

The pitch correction coefficient correction unit 321 generates a correction pitch correction coefficient by correcting the pitch correction coefficient given by the pitch correction coefficient input unit 107 according to the continuation length information given by the continuation length information input unit 320. Then, the generated correction pitch correction coefficient is given to the pitch pattern correction unit 309. As a result, the pitch pattern correction unit 309 can change the correction amount for correcting the pitch pattern according to the prosody of the voice.

The pitch pattern correction unit 309 includes the maximum value indicated by the maximum pitch information given by the maximum pitch specifying unit 103 and the pitch included in the sentence end pitch section indicated by the sentence end pitch section information given by the sentence end pitch section specifying unit 104. The voice utterance style is changed by correcting the pitch pattern given by the pitch pattern acquisition unit 102 according to at least one of them. Here, the pitch pattern correction unit changes the correction amount for correcting the pitch pattern according to the prosody of the voice.

For example, the pitch pattern correction unit 309 stores the pitch pattern correction method corresponding to the utterance style for correcting the pitch pattern given by the pitch pattern acquisition unit 102 in the pitch pattern correction method storage unit 208. Select from.
Then, the pitch pattern correction unit 309 indicates the maximum value indicated by the maximum pitch information given by the maximum pitch specifying unit 103 and the sentence end pitch section information given by the sentence end pitch section specifying unit 104 according to the selected pitch pattern correction method. In the pitch pattern given by the pitch pattern acquisition unit 102, the correction pitch correction coefficient given by the pitch correction coefficient correction unit 321 is used as necessary according to at least one of the pitches included in the end-of-sentence pitch section. The sentence end pitch section indicated by the sentence end pitch section information given by the sentence end pitch section identification unit 104 is corrected.
The corrected pitch pattern is output as a corrected pitch pattern.

The pitch pattern correction device 300 according to the third embodiment can also be realized by the computer 130 shown in FIG.
For example, the memory 131 stores a program that causes the processor 132 to function as a pitch pattern acquisition unit 102, a maximum pitch identification unit 103, a sentence end pitch section identification unit 104, a pitch correction coefficient correction unit 321 and a pitch pattern correction unit 309.

Further, the pitch correction coefficient correction unit 321 can be realized by the network I / F133, the text input I / F134, or the image input I / F135.

FIG. 16 is a flowchart showing the operation of the pitch pattern correction device 300.
First, the pitch pattern acquisition unit 102 receives at least voice information capable of specifying the pitch pattern from the voice information input unit 101, and acquires the pitch pattern specified by the voice information (S30). The processing here is the same as the processing in step S10 in FIG. The acquired pitch pattern is given to the maximum pitch specifying unit 103, the sentence end pitch section specifying unit 104, and the pitch pattern correction unit 309.

Next, the maximum pitch specifying unit 103 identifies the maximum value of the pitch in the trailing phrase from the pitch pattern, and generates maximum pitch information indicating the specified maximum value (S31). The processing here is the same as the processing in step S12 in FIG. Then, the generated maximum pitch information is given to the pitch pattern correction unit 309.

Next, the sentence end pitch section specifying unit 104 identifies the section of the pitch pattern of the sentence end portion from the pitch pattern, and generates sentence end pitch section information indicating the section of the specified pitch pattern (S32). The processing here is the same as the processing in step S13 in FIG. The generated sentence end pitch section information is given to the pitch pattern correction unit 309.

Next, the pitch correction coefficient input unit 107 gives the input pitch correction coefficient to the pitch correction coefficient correction unit 321 (S33). Although the pitch correction coefficient is input in the third embodiment, the third embodiment is not limited to such an example. For example, when the pitch correction coefficient is a fixed value, the value may be included in the program functioning as the pitch correction coefficient correction unit 321. In this case, the pitch correction coefficient input unit 107 may not be provided.

Next, the continuous length information input unit 320 accepts the input of the continuous length information (S34). The input continuation length information is given to the pitch correction coefficient correction unit 321.
In the third embodiment, the continuous length information input unit 320 directly accepts the input of the continuous length information. For example, the pitch correction coefficient correction unit 321 is the voice information input to the voice information input unit 101. Therefore, the continuation length may be specified. In this case, the pitch correction coefficient correction unit 321 may estimate the time information of the phoneme using a known speech recognition method and specify the continuation length of the sentence end pitch section.
Known speech recognition methods are described, for example, in the following documents.
Sadaoki Furui, "Voice Information Processing", 1st Edition, Morikita Publishing Co., Ltd., June 30, 1998, p. 96-105

Next, the pitch correction coefficient correction unit 321 generates a correction pitch correction coefficient by correcting the pitch correction coefficient according to the continuation length information (S35). The generated correction pitch correction coefficient is given to the pitch pattern correction unit 309.

For example, the pitch correction coefficient correction unit 321 may correct the pitch correction coefficient by linear conversion as shown in the following equation (1).
O _w = I _Dur x I _w ÷ Def _Dur (1)

Here, I _w indicates a pitch correction coefficient, I _Dur indicates a continuation length, Def _Dur indicates a preset reference pitch continuation length, and O _w indicates a correction pitch correction coefficient.

Further, a discrete correction pitch correction coefficient is preset in the pitch correction coefficient correction unit 321 according to the continuation length, and the pitch correction coefficient correction unit 321 replaces the pitch correction coefficient with the set correction pitch correction coefficient. You may do so.

Next, the pitch pattern correction unit 309 corrects the pitch pattern (S36). Specifically, it is as follows.
First, the pitch pattern correction unit 309 acquires a pitch pattern correction method corresponding to the utterance style generated by the correction.
Then, the pitch pattern correction unit 309 indicates the maximum value indicated by the maximum pitch information given by the maximum pitch specifying unit 103 and the sentence end pitch section information given by the sentence end pitch section specifying unit 104 by the acquired pitch pattern correction method. The correction pitch correction coefficient given by the pitch correction coefficient correction unit 321 is used as necessary according to at least one of the pitches included in the end-of-sentence pitch section, and the pitch pattern given by the pitch pattern acquisition unit 102 is used. Of these, the sentence end pitch section indicated by the sentence end pitch section information given by the sentence end pitch section identification unit 104 is corrected. The corrected pitch pattern is output as a corrected pitch pattern.

In the flowchart shown in FIG. 16, the processes of steps S31 to S33 can be performed in parallel, and may be performed from any step.

FIG. 17 shows an operation example of the pitch pattern correction unit 309 according to the third embodiment.
It is assumed that the pitch pattern correction method storage unit 208 in the third embodiment stores the pitch pattern correction method information 208a as shown in FIG.

In FIGS. 17A and 17B, the pitch pattern of the non-flat word "Sogune", which has an accent in the first character and has linguistic attribute information of the number 3 mora, is corrected to a question-like pitch pattern. This is an example of the case.
FIG. 17A shows a pitch pattern before correction.
The pitch pattern correction unit 309 corrects the value of the pitch at the rear end in the sentence end pitch section, as shown in FIG. 17B, based on the pitch pattern correction method in which the utterance style is questioned. Here, the correction pitch correction coefficient is "0.8", and the value of the pitch at the rear end is corrected so that the value is lower than the maximum value of the pitch.

In the third embodiment, the pitch correction coefficient is corrected based on the continuation length indicated by the continuation length information, but the third embodiment is not limited to such an example. For example, the pitch correction coefficient may be modified by using the prosody of the spoken voice other than the continuation length of the end-of-sentence pitch section. For example, the pitch correction coefficient may be modified based on the prosody such as the duration or speed of the entire utterance. Further, the pitch correction coefficient may be modified based on the prosody such as the magnitude of intonation.
In addition, the pitch correction coefficient may be modified according to the continuation length or pitch statistics (for example, mean, variance, median, etc.). The pitch correction coefficient may be modified based on the information obtained by combining these.

As described above, according to the third embodiment, the pitch correction coefficient that affects the correction amount can be corrected according to the continuation length. Since the correction amount sufficient for perceiving the utterance style differs depending on the continuation length, the correction amount can be set according to the continuation length, and a natural pitch pattern in which the utterance style is easily perceived can be realized.

In addition to the continuation length of the pitch section at the end of the sentence, if the correction amount is modified using another prosody, it is possible to consider small changes due to the content of the utterance, etc. It is possible to realize a natural pitch pattern that is easily perceived.

The pitch pattern correction device 300 according to the third embodiment includes a language information input unit 105, a language attribute information acquisition unit 106, and a pitch pattern correction method storage unit 108 of the pitch pattern correction device 100 according to the first embodiment. The correction unit 309 may switch the pitch pattern correction method according to the language attribute, as in the first embodiment.

Further, the pitch pattern correction device 300 according to the third embodiment includes the partial pitch correction unit 210 and the maximum pitch identification unit 203 of the pitch pattern correction device 200 according to the second embodiment, and the pitch pattern correction unit 309 is a partial pitch correction unit. The pitch pattern including the specific section corrected by 210 may be corrected.

Embodiment 4.
FIG. 18 is a block diagram schematically showing the configuration of the pitch pattern correction device 400 according to the fourth embodiment.
The pitch pattern correction device 400 includes a voice information input unit 101, a pitch pattern acquisition unit 102, a maximum pitch identification unit 203, a language information input unit 105, a language attribute information acquisition unit 106, and a pitch correction coefficient input unit 107. The pitch pattern correction method storage unit 108, the pitch pattern correction unit 409, the partial pitch correction unit 210, the continuous length information input unit 320, and the pitch correction coefficient correction unit 321 are provided.

Voice information input unit 101, pitch pattern acquisition unit 102, language information input unit 105, language attribute information acquisition unit 106, pitch correction coefficient input unit 107, and pitch pattern correction method storage unit of the pitch pattern correction device 400 according to the fourth embodiment. Reference numeral 108 denotes a voice information input unit 101, a pitch pattern acquisition unit 102, a language information input unit 105, a language attribute information acquisition unit 106, a pitch correction coefficient input unit 107, and a pitch pattern correction unit of the pitch pattern correction device 100 according to the first embodiment. This is the same as the method storage unit 108.

Further, the maximum pitch specifying unit 203 and the partial pitch correction unit 210 of the pitch pattern correction device 400 according to the fourth embodiment are the maximum pitch specifying unit 203 and the partial pitch correction unit 210 of the pitch pattern correction device 200 according to the second embodiment. Is similar to.
Therefore, as shown in FIG. 7, the partial pitch correction unit 210 includes the maximum pitch section extraction unit 211, the maximum pitch section correction method storage unit 212, the maximum pitch section correction unit 213, and the sentence end pitch section extraction. A sentence end pitch section correction method storage unit 216 and a sentence end pitch section correction unit 215 are provided.

Further, the continuous length information input unit 320 and the pitch correction coefficient correction unit 321 of the pitch pattern correction device 400 according to the fourth embodiment are the continuous length information input unit 320 and the pitch correction unit 320 of the pitch pattern correction device 300 according to the third embodiment. This is the same as the coefficient correction unit 321.

The pitch pattern correction unit 409 corresponds to the phonology at the end of the sentence in the pitch pattern including the maximum value indicated by the maximum pitch information given by the maximum pitch identification unit 203 and the specific section corrected by the partial pitch correction unit 210. The voice utterance style is changed by correcting the pitch pattern including the specific section corrected by the partial pitch correction unit 210 according to at least one of the pitches included in the sentence end pitch section which is the section to be performed.

For example, the pitch pattern correction unit 409 includes a pitch pattern indicated by the correction maximum pitch section information given by the maximum pitch section correction unit 213 and a pitch pattern indicated by the correction sentence end pitch section information given by the sentence end pitch section correction unit 215. Is combined with the pitch pattern given by the pitch pattern acquisition unit 102 to generate a partially corrected pitch pattern.

Further, the pitch pattern correction unit 409 stores a pitch pattern correction method corresponding to the language attribute indicated by the language attribute information given by the language attribute information acquisition unit 106 in the pitch pattern correction method storage unit 108. Select from the correction method information.
Then, the pitch pattern correction unit 409 uses the selected pitch pattern correction method to set at least one of the maximum value indicated by the maximum pitch information given by the maximum pitch specifying unit 103 and the pitch included in the sentence end pitch section. Correspondingly, the correction pitch correction coefficient given by the pitch correction coefficient correction unit 321 is used as necessary to correct the partial correction pitch pattern of the section corresponding to the pitch pattern indicated by the given correction sentence end pitch section information.
The corrected partial correction pitch pattern is output as a correction pitch pattern.

The pitch pattern correction device 400 according to the fourth embodiment can also be realized by the computer 130 shown in FIG.
For example, the memory 131 also stores a program that causes the processor 132 to function as the pitch pattern correction unit 409.

FIG. 19 is a flowchart showing the operation of the pitch pattern correction device 400.
First, the pitch pattern acquisition unit 102 receives at least voice information capable of specifying the pitch pattern from the voice information input unit 101, and acquires the pitch pattern specified by the voice information (S40). The processing here is the same as the processing in step S10 shown in FIG. The acquired pitch pattern is given to the maximum pitch section extraction unit 211, the sentence end pitch section extraction unit 214, and the pitch pattern correction unit 409.

Next, the language attribute information acquisition unit 106 receives the language information capable of specifying the language attribute from the language information input unit 105, and acquires the language attribute information indicating the language attribute specified by the language information (S41). ). The processing here is the same as the processing in step S11 of FIG. The acquired language attribute information is given to the pitch pattern correction unit 409.

Next, the maximum pitch section extraction unit 211 extracts the pitch pattern of the maximum pitch section, which is a section corresponding to the phoneme including the maximum value of the pitch in the sentence ending phrase, in the given pitch pattern, and the extracted pitch pattern. The maximum pitch interval extraction information indicating is generated (S42). The processing here is the same as the processing in step S21 of FIG. The generated maximum pitch section extraction information is given to the maximum pitch section correction unit 213.

Next, the sentence end pitch section extraction unit 214 extracts the pitch pattern of the sentence end pitch section including the sentence end pitch in the given pitch pattern, and generates the sentence end pitch section extraction information indicating the extracted pitch pattern (S43). ). The processing here is the same as the processing in step S22 of FIG. The generated sentence end pitch section information is given to the sentence end pitch section correction unit 215.

Next, the pitch correction coefficient input unit 107 gives the input pitch correction coefficient to the pitch correction coefficient correction unit 321 (S44). The processing here is the same as the processing in step S33 of FIG.

Next, the maximum pitch section correction unit 213 corrects the pitch pattern of the maximum section indicated by the given maximum pitch section information according to the maximum pitch section correction method (S45). The processing here is the same as the processing in step S24 of FIG. Then, the maximum pitch section correction unit 213 generates correction maximum pitch section information indicating the corrected pitch pattern, and gives the correction maximum pitch section information to the maximum pitch identification unit 203 and the pitch pattern correction unit 409.

Next, the sentence end pitch section correction unit 215 corrects the pitch pattern of the sentence end section indicated by the given sentence end pitch section information according to the sentence end pitch section correction method (S46). The processing here is the same as the processing in step S25 of FIG. Then, the sentence end pitch section correction unit 215 generates correction sentence end pitch section information indicating the corrected pitch pattern, and gives the correction sentence end pitch section information to the pitch pattern correction unit 409.

Next, the maximum pitch specifying unit 203 specifies the maximum value of the pitch in the pitch pattern indicated by the given corrected maximum pitch section information, and generates the maximum pitch information indicating the specified maximum value (S47). The processing here is the same as the processing in step S26 of FIG. Then, the maximum pitch specifying unit 203 gives the maximum pitch information to the pitch pattern correction unit 409.

Next, the continuous length information input unit 320 accepts the input of the continuous length information (S48). The processing here is the same as the processing in step S34 of FIG. The input continuation length information is given to the pitch correction coefficient correction unit 321.

Next, the pitch correction coefficient correction unit 321 generates a correction pitch correction coefficient by correcting the pitch correction coefficient according to the continuation length information (S49). The processing here is the same as the processing in step S35 of FIG. The generated correction pitch correction coefficient is given to the pitch pattern correction unit 409.

Next, the pitch pattern correction unit 409 corrects the pitch pattern (S50). Specifically, it is as follows.
First, the pitch pattern correction unit 409 synthesizes the pitch pattern indicated by the correction maximum pitch section information and the pitch pattern indicated by the correction sentence end pitch section information into the pitch pattern given by the pitch pattern acquisition unit 102. Generate a partial correction pitch pattern.
Next, the pitch pattern correction unit 409 selects a pitch pattern correction method corresponding to the language attribute indicated by the language attribute information from the pitch pattern correction method information stored in the pitch pattern correction method storage unit 108.
Then, the pitch pattern correction unit 409 responds to at least one of the maximum value indicated by the maximum pitch information given by the maximum pitch specifying unit 103 and the pitch included in the sentence end pitch section by the selected pitch pattern correction method. , The correction pitch correction coefficient given by the pitch correction coefficient correction unit 321 is used as necessary to correct the partial correction pitch pattern of the section corresponding to the pitch pattern indicated by the given correction sentence end pitch section information.

FIG. 20 shows an operation example of the pitch pattern correction unit 409 according to the fourth embodiment.
It is assumed that the pitch pattern correction method storage unit 108 in the fourth embodiment stores the pitch pattern correction method information 108a as shown in FIG.

In FIGS. 20A and 20B, the pitch pattern of the non-flat word "Sogune", which has an accent in the first character and has linguistic attribute information of the number 3 mora, is corrected to a question-like pitch pattern. This is an example of the case.
FIG. 20A shows a partially corrected pitch pattern generated by synthesizing the pitch pattern indicated by the corrected maximum pitch section information and the pitch pattern indicated by the corrected sentence end pitch section information into the pitch pattern. ..
In this case, since the language attribute information indicates "non-flat plate", the pitch pattern correction unit 409 selects, for example, the non-flat plate pitch pattern correction method from the pitch pattern correction method information 108a shown in FIG. To do.

Therefore, as shown in FIG. 20B, the pitch pattern correction unit 409 subtracts the value of the pitch at the beginning of the sentence-end pitch section from the value of the pitch at the end of the sentence-end pitch section, and sets the starting end. The correction is performed by adding to the value of the pitch of. As a result, the value of the pitch at the beginning of the pitch section at the end of the sentence is converted into the value of the pitch at the end before correction.
The terminal pitch value here is a value obtained by multiplying the terminal pitch value in the pitch pattern given by the pitch pattern acquisition unit 102 by the sentence end pitch section correction unit 215 by "0.9". ing.

Further, the pitch pattern correction unit 409 adds a value obtained by integrating the given correction pitch correction coefficient to the difference between the maximum pitch value and the end pitch value of the sentence end pitch section to the end pitch value. The correction is done by that. The maximum value of the pitch here is a value obtained by multiplying the maximum value in the pitch pattern given by the pitch pattern acquisition unit 102 by the maximum pitch section correction unit 213 by "1.2". However, the correction pitch correction coefficient is "0.8".

As described above, according to the fourth embodiment, even when the difference in pitch pattern between the declarative voice and the utterance style is significantly different depending on the language attribute information such as the accent position, the correction method according to the language attribute information. It is possible to correct the inflection that is emphasized or changed depending on the utterance style, and the amount of correction sufficient for perceiving the utterance style differs depending on the duration of the speech, whereas the correction according to the continuation length. You will be able to set the amount. Therefore, there is an effect that the accuracy of prosody correction is improved and a natural pitch pattern in which the utterance style is easily perceived can be realized.

In addition, when statistical values such as the average or median of the pitch in a certain section near the maximum value of the pitch are calculated and configured to be regarded as the maximum value, the influence of outliers due to poor pitch extraction accuracy is suppressed. This has the effect of improving the accuracy of extracting the maximum pitch value.

Further, in step S43, when the change in the pitch pattern due to the utterance style affects the phoneme near the last phoneme, the sentence end pitch section extraction unit 214 extracts the pitch pattern of the section extended to the affected phoneme as the sentence end pitch section information. Then, it is possible to correct the pitch pattern in a flexible range according to the utterance style, and there is an effect that the perceptual accuracy of the utterance style can be improved.

Further, in step S45, when the pitch pattern correction unit 409 corrects the pitch by using the average value of the utterances or the statistical value such as the variance, the correction is performed in consideration of the tendency of the pitch pattern of the entire sentence ending phrase. This has the effect of improving the perceptual accuracy of the speech style.

Further, in step S45, when the pitch pattern correction unit 409 newly prepares a means for extracting the minimum pitch in the phrase and is configured to perform correction in consideration of the minimum pitch, the maximum pitch and the end pitch are close to each other. Even in the case of flat-type utterances, it is possible to make corrections in consideration of the magnitude of intonation, and there is an effect that the perceptual accuracy of the utterance style of the generated pitch pattern can be improved.

In addition to selecting the pitch pattern correction method according to the language attribute information, the language attributes such as accents are also taken into consideration by partially correcting at least one of the maximum pitch section and the sentence end pitch section of the pitch pattern. It is possible to correct the maximum pitch value and the end-of-sentence pitch, improve the accuracy of prosody correction, and have the effect of realizing a natural pitch pattern in which the utterance style is easily perceived.

By selecting the pitch pattern correction method according to the language attribute information and changing the correction amount for correcting the pitch pattern according to the prosody of the voice, for example, from the accent position to the correction section. It is possible to correct the amount of correction in consideration of the distance, improve the accuracy of prosody correction, and have the effect of realizing a natural pitch pattern in which the utterance style is easily perceived.

The maximum pitch is partially corrected by at least one of the maximum pitch section and the end-of-sentence pitch section of the pitch pattern, and the correction amount for correcting the pitch pattern is changed according to the prosody of the voice. It is possible to correct the pitch correction coefficient in consideration of the change in intonation due to the correction of the section and the end-of-sentence pitch section, improve the accuracy of prosody correction, and realize a natural pitch pattern in which the utterance style is easily perceived.

100, 200, 300, 400 Pitch pattern correction device, 101 Voice information input unit, 102 Pitch pattern acquisition unit, 103, 203 Maximum pitch specification unit, 104 Sentence end pitch section specification unit, 105 Language information input unit, 106 Language attribute information acquisition Unit, 107 pitch correction coefficient input unit, 108, 208 pitch pattern correction method storage unit, 109, 209, 309, 409 pitch pattern correction unit, 210 partial pitch correction unit, 211 maximum pitch section extraction unit, 212 maximum pitch section correction method Storage unit, 213 maximum pitch section correction unit, 214 sentence end pitch section extraction unit, 215 sentence end pitch section correction unit, 216 sentence end pitch section correction method storage unit, 320 continuation length information input unit, 321 pitch correction coefficient correction unit.

Claims (11)

A partial pitch correction unit that corrects a specific section in the audio pitch pattern,
In the pitch pattern including the corrected specific section, the maximum pitch specifying unit that specifies the maximum value of the pitch included in the sentence ending phrase in the voice, and
Depending on at least one of the specified maximum value and the pitch included in the sentence end pitch section, which is the section corresponding to the phoneme at the end of the sentence in the pitch pattern including the corrected specific section. It is provided with a pitch pattern correction unit that changes the utterance style of the voice by correcting the pitch pattern including the corrected specific section .
The pitch pattern correction device, characterized in that the specific section is a section corresponding to a phoneme including the maximum value of the pitch included in the sentence ending phrase in the voice . A partial pitch correction unit that corrects a specific section in the audio pitch pattern,
In the pitch pattern including the corrected specific section, the maximum pitch specifying unit that specifies the maximum value of the pitch included in the sentence ending phrase in the voice, and
Depending on at least one of the specified maximum value and the pitch included in the sentence end pitch section, which is the section corresponding to the phoneme at the end of the sentence in the pitch pattern including the corrected specific section. It is provided with a pitch pattern correction unit that changes the utterance style of the voice by correcting the pitch pattern including the corrected specific section .
The pitch pattern correction device, characterized in that the specific section is a section corresponding to the starting pitch included in the sentence ending phrase in the voice . A partial pitch correction unit that corrects a specific section in the audio pitch pattern,
In the pitch pattern including the corrected specific section, the maximum pitch specifying unit that specifies the maximum value of the pitch included in the sentence ending phrase in the voice, and
Depending on at least one of the specified maximum value and the pitch included in the sentence end pitch section, which is the section corresponding to the phoneme at the end of the sentence in the pitch pattern including the corrected specific section. It is provided with a pitch pattern correction unit that changes the utterance style of the voice by correcting the pitch pattern including the corrected specific section .
The pitch pattern correction device, characterized in that the specific section is a section corresponding to the minimum value of the pitch included in the sentence ending phrase in the voice . The claim is characterized in that the pitch pattern correction unit switches a pitch pattern correction method which is a method of correcting a pitch pattern including the corrected specific section according to a language attribute which is a language attribute in the voice. Item 2. The pitch pattern correction device according to any one of Items 1 to 3 . The pitch pattern correction unit according to any one of claims 1 to 4 , wherein the correction amount for correcting the pitch pattern including the corrected specific section is changed according to the prosody of the voice. The pitch pattern correction device described. Computer,
Partial pitch correction unit that corrects a specific section in the voice pitch pattern,
In the pitch pattern including the corrected specific section, the maximum pitch specifying unit that specifies the maximum value of the pitch included in the sentence ending phrase in the voice, and the maximum pitch specifying unit, and
Depending on at least one of the specified maximum value and the pitch included in the sentence end pitch section, which is the section corresponding to the phoneme at the end of the sentence in the pitch pattern including the corrected specific section. By correcting the pitch pattern including the corrected specific section, it functions as a pitch pattern correction unit that changes the utterance style of the voice .
The specific section is a section corresponding to a phoneme including the maximum value of the pitch included in the sentence ending phrase in the voice . Computer,
Partial pitch correction unit that corrects a specific section in the voice pitch pattern,
In the pitch pattern including the corrected specific section, the maximum pitch specifying unit that specifies the maximum value of the pitch included in the sentence ending phrase in the voice, and the maximum pitch specifying unit, and
Depending on at least one of the specified maximum value and the pitch included in the sentence end pitch section, which is the section corresponding to the phoneme at the end of the sentence in the pitch pattern including the corrected specific section. By correcting the pitch pattern including the corrected specific section, it functions as a pitch pattern correction unit that changes the utterance style of the voice.
The specific section is a section corresponding to the starting pitch included in the sentence ending phrase in the voice.
A program featuring. Computer,
Partial pitch correction unit that corrects a specific section in the voice pitch pattern,
In the pitch pattern including the corrected specific section, the maximum pitch specifying unit that specifies the maximum value of the pitch included in the sentence ending phrase in the voice, and the maximum pitch specifying unit, and
Depending on at least one of the specified maximum value and the pitch included in the sentence end pitch section, which is the section corresponding to the phoneme at the end of the sentence in the pitch pattern including the corrected specific section. By correcting the pitch pattern including the corrected specific section, it functions as a pitch pattern correction unit that changes the utterance style of the voice.
The specific section is a section corresponding to the minimum value of the pitch included in the sentence ending phrase in the voice.
A program featuring. In the audio pitch pattern, correct a specific section and
In the pitch pattern including the corrected specific section, the maximum value of the pitch included in the sentence ending phrase in the voice is specified, and
Depending on at least one of the specified maximum value and the pitch included in the sentence end pitch section, which is the section corresponding to the phoneme at the end of the sentence in the pitch pattern including the corrected specific section. It is a pitch pattern correction method that changes the utterance style of the voice by correcting the pitch pattern including the corrected specific section .
The pitch pattern correction method, characterized in that the specific section is a section corresponding to a phoneme including the maximum value of the pitch included in the sentence ending phrase in the voice . In the audio pitch pattern, correct a specific section and
In the pitch pattern including the corrected specific section, the maximum value of the pitch included in the sentence ending phrase in the voice is specified, and
Depending on at least one of the specified maximum value and the pitch included in the sentence end pitch section, which is the section corresponding to the phoneme at the end of the sentence in the pitch pattern including the corrected specific section. It is a pitch pattern correction method that changes the utterance style of the voice by correcting the pitch pattern including the corrected specific section.
The specific section is a section corresponding to the starting pitch included in the sentence ending phrase in the voice.
A pitch pattern correction method characterized by. In the audio pitch pattern, correct a specific section and
In the pitch pattern including the corrected specific section, the maximum value of the pitch included in the sentence ending phrase in the voice is specified, and
Depending on at least one of the specified maximum value and the pitch included in the sentence end pitch section, which is the section corresponding to the phoneme at the end of the sentence in the pitch pattern including the corrected specific section. It is a pitch pattern correction method that changes the utterance style of the voice by correcting the pitch pattern including the corrected specific section.
The specific section is a section corresponding to the minimum value of the pitch included in the sentence ending phrase in the voice.
A pitch pattern correction method characterized by.

Images